Dear Colleagues,

Deep learning has been an active topic in machine learning and has become the dominant approach in several domains, such as computer vision and natural language processing. In biomedical and medical image processing, machine learning paradigms, including supervised, self-supervised, unsupervised, and reinforcement learning, have been considered for various applications, such as image classification, segmentation, and detection. In supervised learning, convolutional neural networks are one of the most prevalent architectures to train labelled images, and have shown applicability in biomedical and medical image processing. Self-supervised, along with unsupervised learning, allows for the automatic discovery of important image features and assists in the interpretation of image characteristics. In addition, reinforcement learning has a unique approach based on indirect indication, called reward, and can contribute to image analysis and the optimization of hyperparameters including neural network architectures.

Although impressive results have been reported in biomedical and medical images, given the high stakes of this domain, there are several challenges that need to be addressed before these methods are widely adopted. Transfer learning is a well-known strategy in deep learning to overcome data scarcity, and its efficacy in medical image processing has been reported. However, most studies provide heuristic results without providing generalized rules for application in a specific application. Furthermore, the interpretability of deep learning algorithms can provide an in-depth explanation of their behavior. Nevertheless, despite its importance, the robustness of deep learning algorithms is still underexplored. Understanding these characteristics could help to expand the use of deep learning in biomedical and medical processing.

In this Special Issue, we welcome contributions that address these challenges and could lead to the wider adoption of deep learning in medical imaging.

Dr. Jihye Bae
Dr. Andres Alvarez-Meza
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• supervised learning
• self-supervised learning
• unsupervised learning
• reinforcement learning
• transfer learning
• interpretable models
• robust methods